The NVIDIA DGX B300 is a purpose-built AI infrastructure solution tailored to meet the computational demands of generative AI and large-scale reasoning. Powered by NVIDIA Blackwell Ultra GPUs, it provides a unified platform for accelerating large language model (LLM) inference and training with hyperscaler-class efficiency.
- Features 8x NVIDIA Blackwell Ultra SXM GPUs for industry-leading AI compute.
- Delivers 144 PFLOPS of FP4 Tensor Core performance for advanced AI reasoning.
- Integrated with 2.1 TB of total GPU memory to support massive model architectures.
- Powered by Intel Xeon 6776P processors for high-performance host processing.
- Provides 14.4 TB/s aggregate bandwidth via NVIDIA NVLink Switch System.
- Includes 8x OSFP ports for up to 800 Gb/s InfiniBand or Ethernet connectivity.
- Equipped with dual NVIDIA BlueField-3 DPUs for accelerated networking and security.
- Redesigned 10U form factor compatible with NVIDIA MGX and enterprise racks.
- Internal storage includes 8x 3.84 TB NVMe E1.S drives for high-speed data access.
- Optimized for energy efficiency with multiple AC and DC power configuration options.
NVIDIA - DGX B300 - AI Infrastructure System
For a quote, contact us at info@tropical.com
- SKU:
- DGX B300
- Weight:
- 350.00 LBS
- Width:
- 19.00 (in)
- Height:
- 17.50 (in)
- Depth:
- 35.40 (in)
Related Products
A relatable product
NVIDIA - DGX H200 - AI Infrastructure System
The NVIDIA DGX H200 is the premier AI factory infrastructure designed for enterprise-scale generative AI, natural language processing, and deep learning. It integrates eight NVIDIA H200 Tensor Core...
NVIDIA - DGX A100 - AI Infrastructure System
The NVIDIA DGX A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world's first 5-petaFLOPS AI system. It integrates eight...
NVIDIA - DGX GB200 - Rack-Scale AI Infrastructure System
The NVIDIA DGX GB200 is a rack-scale AI factory purpose-built for training and inferencing trillion-parameter generative AI models. It integrates 36 NVIDIA GB200 Grace Blackwell Superchips into a...
NVIDIA
NVIDIA - DGX A100 640GB Config - AI Infrastructure System
The NVIDIA DGX A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world's first 5-petaFLOPS AI system. Featuring eight...
NVIDIA
NVIDIA - DGX H200 NVLink System - AI Supercomputing Infrastructure
The NVIDIA DGX H200 is the world’s premier AI platform, purpose-built for the most demanding generative AI and high-performance computing (HPC) workloads. It leverages the NVIDIA H200 Tensor Core GPU...